Multi-Window Identification of Landslide Hazards Based on InSAR Technology and Factors Predisposing to Disasters
Identification of potential landslide hazards is of great significance for disaster prevention and control. CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks) and many other deep learning methods have been used to identify landslide hazards. However, most samples are made with a fi...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Land |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-445X/12/1/173 |
| _version_ | 1797439846608797696 |
|---|---|
| author | Chong Niu Wenping Yin Wei Xue Yujing Sui Xingqing Xun Xiran Zhou Sheng Zhang Yong Xue |
| author_facet | Chong Niu Wenping Yin Wei Xue Yujing Sui Xingqing Xun Xiran Zhou Sheng Zhang Yong Xue |
| author_sort | Chong Niu |
| collection | DOAJ |
| description | Identification of potential landslide hazards is of great significance for disaster prevention and control. CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks) and many other deep learning methods have been used to identify landslide hazards. However, most samples are made with a fixed window size, which affects recognition accuracy to some extent. This paper presents a multi-window hidden danger identification CNN method according to the scale of the landslide in the experimental area. Firstly, the hidden danger area is preliminarily screened by InSAR deformation processing technology. Secondly, based on topography, geology, hydrology and human activities, a total of 15 disaster-prone factors are used to create factor datasets for in-depth learning. According to the general scale of the landslide, models with four window sizes of 48 × 48, 32 × 32, 16 × 16 and 8 × 8 are trained, respectively, and several window models with better recognition effect and suitable for the scale of landslide in the experimental area are selected for the accurate identification of landslide hazards. The results show that, among the four windows, 16 × 16 and 8 × 8 windows have the best model recognition effect. Then, according to the scale of the landslide, these optimal windows are pertinently selected, and the precision, recall rate and F-measure of the multi-window deep learning model are improved (82.86%, 78.75%, 80.75%). The research results prove that the multi-window identification method of landslide hazards combining InSAR technology and factors predisposing to disasters is effective, which can play an important role in regional disaster identification and enhance the scientific and technological support ability of geological disaster prevention and mitigation. |
| first_indexed | 2024-03-09T11:59:37Z |
| format | Article |
| id | doaj.art-77275700d8b3421a861a1b99dd930a81 |
| institution | Directory Open Access Journal |
| issn | 2073-445X |
| language | English |
| last_indexed | 2024-03-09T11:59:37Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Land |
| spelling | doaj.art-77275700d8b3421a861a1b99dd930a812023-11-30T23:05:20ZengMDPI AGLand2073-445X2023-01-0112117310.3390/land12010173Multi-Window Identification of Landslide Hazards Based on InSAR Technology and Factors Predisposing to DisastersChong Niu0Wenping Yin1Wei Xue2Yujing Sui3Xingqing Xun4Xiran Zhou5Sheng Zhang6Yong Xue7School of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaShandong GEO-Surveying and Mapping Institute, Jinan 250002, ChinaShandong GEO-Surveying and Mapping Institute, Jinan 250002, ChinaShandong GEO-Surveying and Mapping Institute, Jinan 250002, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaSchool of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, ChinaIdentification of potential landslide hazards is of great significance for disaster prevention and control. CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks) and many other deep learning methods have been used to identify landslide hazards. However, most samples are made with a fixed window size, which affects recognition accuracy to some extent. This paper presents a multi-window hidden danger identification CNN method according to the scale of the landslide in the experimental area. Firstly, the hidden danger area is preliminarily screened by InSAR deformation processing technology. Secondly, based on topography, geology, hydrology and human activities, a total of 15 disaster-prone factors are used to create factor datasets for in-depth learning. According to the general scale of the landslide, models with four window sizes of 48 × 48, 32 × 32, 16 × 16 and 8 × 8 are trained, respectively, and several window models with better recognition effect and suitable for the scale of landslide in the experimental area are selected for the accurate identification of landslide hazards. The results show that, among the four windows, 16 × 16 and 8 × 8 windows have the best model recognition effect. Then, according to the scale of the landslide, these optimal windows are pertinently selected, and the precision, recall rate and F-measure of the multi-window deep learning model are improved (82.86%, 78.75%, 80.75%). The research results prove that the multi-window identification method of landslide hazards combining InSAR technology and factors predisposing to disasters is effective, which can play an important role in regional disaster identification and enhance the scientific and technological support ability of geological disaster prevention and mitigation.https://www.mdpi.com/2073-445X/12/1/173landslide hazard identificationdeep learningmulti-windowInSARfactors predisposing to disasters |
| spellingShingle | Chong Niu Wenping Yin Wei Xue Yujing Sui Xingqing Xun Xiran Zhou Sheng Zhang Yong Xue Multi-Window Identification of Landslide Hazards Based on InSAR Technology and Factors Predisposing to Disasters Land landslide hazard identification deep learning multi-window InSAR factors predisposing to disasters |
| title | Multi-Window Identification of Landslide Hazards Based on InSAR Technology and Factors Predisposing to Disasters |
| title_full | Multi-Window Identification of Landslide Hazards Based on InSAR Technology and Factors Predisposing to Disasters |
| title_fullStr | Multi-Window Identification of Landslide Hazards Based on InSAR Technology and Factors Predisposing to Disasters |
| title_full_unstemmed | Multi-Window Identification of Landslide Hazards Based on InSAR Technology and Factors Predisposing to Disasters |
| title_short | Multi-Window Identification of Landslide Hazards Based on InSAR Technology and Factors Predisposing to Disasters |
| title_sort | multi window identification of landslide hazards based on insar technology and factors predisposing to disasters |
| topic | landslide hazard identification deep learning multi-window InSAR factors predisposing to disasters |
| url | https://www.mdpi.com/2073-445X/12/1/173 |
| work_keys_str_mv | AT chongniu multiwindowidentificationoflandslidehazardsbasedoninsartechnologyandfactorspredisposingtodisasters AT wenpingyin multiwindowidentificationoflandslidehazardsbasedoninsartechnologyandfactorspredisposingtodisasters AT weixue multiwindowidentificationoflandslidehazardsbasedoninsartechnologyandfactorspredisposingtodisasters AT yujingsui multiwindowidentificationoflandslidehazardsbasedoninsartechnologyandfactorspredisposingtodisasters AT xingqingxun multiwindowidentificationoflandslidehazardsbasedoninsartechnologyandfactorspredisposingtodisasters AT xiranzhou multiwindowidentificationoflandslidehazardsbasedoninsartechnologyandfactorspredisposingtodisasters AT shengzhang multiwindowidentificationoflandslidehazardsbasedoninsartechnologyandfactorspredisposingtodisasters AT yongxue multiwindowidentificationoflandslidehazardsbasedoninsartechnologyandfactorspredisposingtodisasters |